Efficient Subpixel Refinement with Symbolic Linear Predictors

TL;DR

This paper introduces Symbolic Linear Predictors, a learning-based subpixel refinement method that is both efficient and accurate, suitable for online applications and resource-constrained environments.

Contribution

It proposes Symbolic Linear Predictors to make learning-based subpixel refinement more efficient and introduces a way to predict alignment error for better keypoint selection.

Findings

Method achieves high accuracy in subpixel refinement.

Approach is suitable for online and resource-constrained applications.

Extensive experiments demonstrate efficiency and effectiveness.

Abstract

We present an efficient subpixel refinement method usinga learning-based approach called Linear Predictors. Two key ideas are shown in this paper. Firstly, we present a novel technique, called Symbolic Linear Predictors, which makes the learning step efficient for subpixel refinement. This makes our approach feasible for online applications without compromising accuracy, while taking advantage of the run-time efficiency of learning based approaches. Secondly, we show how Linear Predictors can be used to predict the expected alignment error, allowing us to use only the best keypoints in resource constrained applications. We show the efficiency and accuracy of our method through extensive experiments.